CCM
/MCP
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Claude Code Marketplaces

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Skill index
  • MCP index
  • Marketplace index
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by mertbuilds.com

Independent project, not affiliated with Anthropic
wyre-technology avatar

Rootly

wyre-technology/rootly-mcp
authSTDIOregistry active
Summary

Connects Claude to the Rootly incident management platform via their v1 REST API. Exposes tools for creating, listing, and resolving incidents and alerts, querying on-call schedules, and fetching team and severity metadata. Uses a decision tree navigation pattern where you call rootly_navigate to pick a domain like incidents or alerts, then use that domain's tools until you navigate back. Handles Rootly's 3 write operations per 60 seconds rate limit with in-process tracking. Supports both stdio and HTTP streaming transports, with Docker images available at ghcr.io. Built by WYRE Technology as part of their wyre-projects collection.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Lid closed, agents working
Lid closed, agents working
Keeps your Mac awake while Claude Code, Codex or Cursor works. Lets it sleep when they are done.
Try free for 7 days →
Block distraction from your iPhone for freeBlock distraction from your iPhone for free
Block distraction from your iPhone for free
Block distracting apps from your iPhone permanently without a 3rd party app. Free and open source.
Block now (100% free) →
Granola, the best AI meeting recorder
Granola, the best AI meeting recorder
Notes, actions and memory. Without a meeting bot. First month 100% off.
Download for free →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Open Steps
Open Steps
Free an open-source skills that make AI coding agents easier to understand, verify, and control.
Download for free →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
Agent, connect blockchain
Agent, connect blockchain
Connect your Claude agent to live crypto prices and trading routes via 1inch
Get the MCP →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Lid closed, agents working
Lid closed, agents working
Keeps your Mac awake while Claude Code, Codex or Cursor works. Lets it sleep when they are done.
Try free for 7 days →
Block distraction from your iPhone for freeBlock distraction from your iPhone for free
Block distraction from your iPhone for free
Block distracting apps from your iPhone permanently without a 3rd party app. Free and open source.
Block now (100% free) →
Granola, the best AI meeting recorder
Granola, the best AI meeting recorder
Notes, actions and memory. Without a meeting bot. First month 100% off.
Download for free →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Open Steps
Open Steps
Free an open-source skills that make AI coding agents easier to understand, verify, and control.
Download for free →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
Agent, connect blockchain
Agent, connect blockchain
Connect your Claude agent to live crypto prices and trading routes via 1inch
Get the MCP →

rootly-mcp

MCP server for the Rootly incident management platform.

Built by WYRE Technology — part of the wyre-projects MCP server collection.

Uses decision-tree navigation: start with rootly_navigate to select a domain, then use that domain's tools. Call rootly_back to return.

Domains & Tools

Navigation (always available)

ToolDescription
rootly_navigateNavigate to a domain: incidents, alerts, schedules, org
rootly_statusCheck connection status and available domains
rootly_backReturn to the navigation menu

Domain: incidents

ToolDescription
rootly_incidents_listList incidents with optional status/severity filters
rootly_incidents_getGet a single incident by ID
rootly_incidents_createCreate a new incident
rootly_incidents_updateUpdate title, summary, status, or severity
rootly_incidents_resolveResolve an incident

Domain: alerts

ToolDescription
rootly_alerts_listList alerts with optional status filter
rootly_alerts_acknowledgeAcknowledge an alert
rootly_alerts_resolveResolve an alert
rootly_alerts_createCreate a new alert
rootly_alerts_updateUpdate alert status or summary

Domain: schedules

ToolDescription
rootly_schedules_listList on-call schedules
rootly_schedules_getGet a single on-call schedule

Domain: org

ToolDescription
rootly_org_list_teamsList teams
rootly_org_list_severitiesList severity levels
rootly_org_current_userGet current authenticated user

Interactive Incident Card (MCP Apps)

rootly_incidents_get renders as an interactive read-only card in MCP Apps hosts (Claude Desktop/web) showing status, severity, services, environments, teams, and a lifecycle timeline; plain-JSON behavior is unchanged in other hosts. The card is neutral by default and brandable via window.__BRAND__ injection or MCP_BRAND_* env vars (MCP_BRAND_NAME, MCP_BRAND_LOGO_URL, MCP_BRAND_PRIMARY_COLOR, MCP_BRAND_ACCENT_COLOR, MCP_BRAND_BG, MCP_BRAND_TEXT) — no rebuild needed. Rebuild the card bundle itself with npm run build:ui (only needed when ui/ changes; the embedded output is committed).

Setup

1. Install & build

cd rootly-mcp
npm install
npm run build

2. Set your API token

export ROOTLY_API_TOKEN=rootly_xxxxxxxxxxxxxxxx

Get your token from Rootly → Profile → API Tokens.

3. Run (stdio — for mcporter/Claude Desktop)

ROOTLY_API_TOKEN=your_token node dist/index.js

4. Run (HTTP streaming transport)

CONDUIT_S2S_SECRET is required. If it is empty or a known placeholder (changeme, change-me, secret, example, placeholder, replace-me, your-secret, your-s2s-secret, s2s-secret, replace-with-a-real-secret), the HTTP server logs an error and exits non-zero. It never prints the secret.

# Refuses to start until CONDUIT_S2S_SECRET is set. With a secret and no
# MCP_HTTP_HOST, the process binds 0.0.0.0 (same as container deploys).
CONDUIT_S2S_SECRET="$CONDUIT_S2S_SECRET" \
  ROOTLY_API_TOKEN=your_token \
  MCP_HTTP_HOST=127.0.0.1 \
  npm run start:http

# Local HTTP only, without a service-to-service secret. Always binds 127.0.0.1.
# A non-loopback MCP_HTTP_HOST is overridden and that override is logged.
MCP_ALLOW_INSECURE_DEV=1 npm run start:http

/health stays unauthenticated, does not require X-Gateway-S2S, and does not return the API token. The stdio transport does not use CONDUIT_S2S_SECRET.

5. Run with Docker

The image listens on 0.0.0.0 inside the container (MCP_HTTP_HOST) and defaults to AUTH_MODE=gateway. Publish the port on loopback and pass the S2S secret. In gateway mode the Rootly token arrives on each request as X-Rootly-Api-Token; it is not read from the environment.

docker build -t rootly-mcp .
docker run \
  -e CONDUIT_S2S_SECRET="$(openssl rand -hex 32)" \
  -p 127.0.0.1:8080:8080 \
  rootly-mcp

Do not pass a known placeholder such as your-s2s-secret or changeme. Startup treats those as unset and exits. Compose refuses to start when CONDUIT_S2S_SECRET is unset, sets AUTH_MODE=gateway, does not pass ROOTLY_API_TOKEN, and publishes 127.0.0.1:8080:8080. A project .env is interpolation only — do not add env_file to the gateway service.

CONDUIT_S2S_SECRET="$(openssl rand -hex 32)" docker compose up

Single-tenant HTTP (AUTH_MODE=env) still requires the S2S secret, then uses ROOTLY_API_TOKEN:

docker run \
  -e CONDUIT_S2S_SECRET="$(openssl rand -hex 32)" \
  -e AUTH_MODE=env \
  -e ROOTLY_API_TOKEN=your_token \
  -e MCP_HTTP_HOST=0.0.0.0 \
  -p 127.0.0.1:8080:8080 \
  rootly-mcp

Configuration

Copy .env.example and set the variables below.

VariableRequiredDescription
ROOTLY_API_TOKENFor stdio and AUTH_MODE=envRootly API token (Bearer). Gateway mode does not read this.
MCP_TRANSPORTNostdio (default) or http
AUTH_MODENogateway (Docker image and Compose default) or env. Gateway mode requires X-Rootly-Api-Token on each /mcp request and never falls back to ROOTLY_API_TOKEN. env uses that variable after S2S auth succeeds.
CONDUIT_S2S_SECRETYes for HTTPService-to-service secret. The HTTP server logs an error and exits non-zero when this is empty or a known placeholder. Compose will not start without it. Never commit a real value.
MCP_ALLOW_INSECURE_DEVNoSet to exactly 1 only for local development to start HTTP without CONDUIT_S2S_SECRET. The process logs a warning, does not enforce X-Gateway-S2S, and binds 127.0.0.1 only. A non-loopback MCP_HTTP_HOST is overridden and logged. A placeholder secret still refuses to start.
MCP_HTTP_HOSTNoBind address when a secret is configured. Unset means 0.0.0.0. The container image sets 0.0.0.0. Ignored in favor of 127.0.0.1 when the insecure-dev bypass is on.
MCP_HTTP_PORTNoHTTP port. Defaults to 8080.
LOG_LEVELNodebug, info, warn, or error. Defaults to info.

HTTP authentication

With MCP_TRANSPORT=http and CONDUIT_S2S_SECRET set, every /mcp request must include X-Gateway-S2S. The value is t=<unix seconds>,v1=<hex hmac-sha256>. The hex digest is HMAC-SHA256 over the exact ASCII string t=<unix seconds> (the same prefix that appears in the header), keyed with CONDUIT_S2S_SECRET, encoded as 64 lowercase hex characters. The timestamp must be within 300 seconds of the server clock. A missing or invalid header returns 401. The secret is never written to logs or the response.

X-Gateway-S2S: t=1710000000,v1=<64 lowercase hex chars>

In AUTH_MODE=gateway, /mcp also requires X-Rootly-Api-Token. That header is the only Rootly credential for the request. A request without it returns 401 and does not fall back to ROOTLY_API_TOKEN.

curl -sS http://127.0.0.1:8080/mcp \
  -H 'content-type: application/json' \
  -H 'accept: application/json, text/event-stream' \
  -H "x-gateway-s2s: $X_GATEWAY_S2S" \
  -H "x-rootly-api-token: $ROOTLY_API_TOKEN" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"rootly_status","arguments":{}}}'

mcporter Configuration

{
  "rootly": {
    "command": "node",
    "args": ["/path/to/rootly-mcp/dist/index.js"],
    "env": {
      "ROOTLY_API_TOKEN": "rootly_xxxxxxxxxxxxxxxx"
    }
  }
}

Then: mcporter call rootly.rootly_navigate --domain alerts

Claude Desktop (MCPB)

Download the .mcpb bundle from Releases and install it in Claude Desktop.

Or manually add to claude_desktop_config.json:

{
  "mcpServers": {
    "rootly": {
      "command": "node",
      "args": ["/path/to/rootly-mcp/dist/index.js"],
      "env": { "ROOTLY_API_TOKEN": "your_token" }
    }
  }
}

Rate Limiting

Rootly enforces 3 write operations per 60 seconds. The server tracks this in-process and returns a descriptive error with retry-after time if exceeded.

API Reference

  • Rootly API docs: https://docs.rootly.com/api-reference
  • API base URL: https://api.rootly.com/v1
  • Auth: Authorization: Bearer <token>
  • Write content-type: application/vnd.api+json

Development

npm run dev        # watch mode
npm run lint       # TypeScript type-check
npm run test       # run tests

License

Apache-2.0 © WYRE Technology

Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Lid closed, agents working
Lid closed, agents working
Keeps your Mac awake while Claude Code, Codex or Cursor works. Lets it sleep when they are done.
Try free for 7 days →
Block distraction from your iPhone for freeBlock distraction from your iPhone for free
Block distraction from your iPhone for free
Block distracting apps from your iPhone permanently without a 3rd party app. Free and open source.
Block now (100% free) →
Granola, the best AI meeting recorder
Granola, the best AI meeting recorder
Notes, actions and memory. Without a meeting bot. First month 100% off.
Download for free →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Open Steps
Open Steps
Free an open-source skills that make AI coding agents easier to understand, verify, and control.
Download for free →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
Agent, connect blockchain
Agent, connect blockchain
Connect your Claude agent to live crypto prices and trading routes via 1inch
Get the MCP →

Configuration

ROOTLY_API_TOKEN*secret

Rootly API token (Bearer credential)

MCP_TRANSPORTdefault: stdio

Transport mode for the server. Set to 'stdio' for local CLI use; the image defaults to 'http' for gateway hosting.

AUTH_MODEdefault: env

Credential source: 'env' reads vars locally, 'gateway' expects header injection from the WYRE MCP Gateway.

LOG_LEVELdefault: info

Log verbosity: debug, info, warn, error

Categories
Monitoring & Observability
Registryactive
Packageghcr.io/wyre-technology/rootly-mcp:v1.1.7
TransportSTDIO
AuthRequired
UpdatedMay 30, 2026
View on GitHub

More from wyre-technology

  • SalesBuildr
  • SentinelOne (Purple)
  • Sherweb
  • Spanning Cloud Backup
  • Autotask42
  • IT Glue12
  • NinjaOne18
  • ConnectWise Manage7
  • CIPP5
  • Datto RMM3
  • Hudu3
  • Syncro3
  • Action12
  • QuickBooks Online2
  • Avanan1
  • ConnectWise Automate1
  • HaloPSA1
  • SuperOps1
  • Xero1
  • Huntress1
  • ThreatLocker1
  • Abnormal Security
  • Alternative Payments
  • Auvik

Related Monitoring & Observability MCP Servers

View all →
yakenator avatar
Web Auditor

yakenator/web-inspector

Analyze web pages and entire sites for SEO, accessibility, performance, and security compliance. Generate detailed reports and actionable issue lists to improve site quality and user experience. Track historical audit data to monitor improvements across multiple crawl sessions.
infoinlet-marketplace avatar
Mcp Observability

io.github.infoinlet-marketplace/mcp-observability

Observability for incident agents — query Loki (LogQL), Prometheus (PromQL), Elasticsearch.
betterdb-inc avatar
Monitor

betterdb-inc/monitor

BetterDB MCP server - Valkey observability for Claude Code and other MCP clients
1.1k
mcparmory avatar
Datadog

com.mcparmory/datadog

Monitor infrastructure, manage agents and deployments, track metrics, logs, and events
25
thotischner avatar
Observability Mcp

thotischner/observability-mcp

Unified observability gateway for AI agents — Prometheus, Loki & more, with anomaly detection.
5
tantiope avatar
Datadog Mcp

io.github.tantiope/datadog-mcp

Full Datadog API access: monitors, logs, metrics, traces, dashboards, and observability tools
4